A context-aware Model Context Protocol (MCP) server that provides semantic search capabilities across your codebase using Qdrant vector database. Now with (v0.3.0), (v0.3.4), and (v0.3.4.post4).
概览
A context-aware Model Context Protocol (MCP) server that provides semantic search capabilities across your codebase using Qdrant vector database. Now with (v0.3.0), (v0.3.4), and (v0.3.4.post4). Designed to work seamlessly with Claude Code. This server enables AI agents to efficiently work with entire codebases while using 95%+ fewer tokens. Learn how → - : RAG-powered GitHub issue analysis and automated fix generation - : Analyze issues → Generate fixes → Create PRs with dry-run safety - : Create projects, manage roadmaps, track progress with custom dashboards - : Complete issue lifecycle + 8 project management tools + 5 sub-issues tools via natural language - : Break down complex work with parent/child issue relationships - List, add, remove, create, and reorder sub-issues - Bulk add sub-issues to Projects V2 with smart field assignment - Re-parenting support for reorganizing work - Automatic issue number to ID conversion for intuitive usage - : Add comments to existing issues for...
README
以下为原文 README 节选，完整内容请查看原文。
Qdrant RAG MCP Server
A context-aware Model Context Protocol (MCP) server that provides semantic search capabilities across your codebase using Qdrant vector database. Now with intelligent GitHub issue resolution (v0.3.0), GitHub Projects V2 management (v0.3.4), and hierarchical sub-issues support (v0.3.4.post4). Designed to work seamlessly with Claude Code.
Why MCP RAG? This server enables AI agents to efficiently work with entire codebases while using 95%+ fewer tokens. Learn how →
🌟 Features
🆕 GitHub Integration (v0.3.0) + Projects V2 (v0.3.4) + Sub-Issues (v0.3.4.post4)
- 🤖 Intelligent Issue Resolution: RAG-powered GitHub issue analysis and automated fix generation
- 🔄 End-to-End Workflows: Analyze issues → Generate fixes → Create PRs with dry-run safety
- 📋 GitHub Projects V2 Management: Create projects, manage roadmaps, track progress with custom dashboards
- 🎯 29 GitHub MCP Tools: Complete issue lifecycle + 8 project management tools + 5 sub-issues tools via natural language
- 📑 Hierarchical Sub-Issues: Break down complex work with parent/child issue relationships
- List, add, remove, create, and reorder sub-issues
- Bulk add sub-issues to Projects V2 with smart field assignment
- Re-parenting support for reorganizing work
- Automatic issue number to ID conversion for intuitive usage
- 💬 Issue Comments: Add comments to existing issues for workflow updates and collaboration
- 🧠 Smart Project Assignment: RAG-enhanced field assignment based on issue content analysis
- 📊 Project Templates: Pre-built templates for roadmaps, bug tracking, and feature planning
- 🔐 Flexible Authentication: Personal Access Token and GitHub App support
- 📊 RAG-Enhanced Analysis: Leverage full codebase search for issue understanding
- 🛡️ Safety-First Design: Dry-run mode, file protection, rate limiting, and audit logging
🆕 Context Tracking (v0.3.1)
- 👁️ Context Window Visibility: Monitor what Claude knows in the current session
- 📊 Token Usage Tracking: Real-time estimates of context window consumption
- ⚠️ Usage Warnings: Automatic alerts at 60% and 80% context usage
- 📈 Session Timeline: Chronological view of all context-consuming operations
- 💾 Session Persistence: Automatic saving for later analysis
- 🔍 Session Viewer: Utility to analyze patterns across sessions
🆕 Specialized Embeddings (v0.3.3)
- 🎯 Content-Type Specific Models: Different AI models optimized for different content types
- Code: Programming-aware embeddings for 30-50% better code search relevance
- Config: Structure-aware models for precise JSON/YAML/XML navigation
- Documentation: Prose-optimized embeddings for natural documentation search
- 🧠 Language-Specific Understanding: Python idioms, JavaScript patterns, and more
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"qdrant-rag": {
"command": "python",
"args": ["/path/to/qdrant-rag/src/qdrant_mcp_context_aware.py"],
"env": {
"MCP_CLIENT_CWD": "${workspaceFolder}"
}
}
}
}